agentlans/low-readability-text
Viewer • Updated • 187k • 28
Alan Tseng
agentlans
AI & ML interests
Small data, boring AI
Recent Activity
updated a dataset 1 day ago
agentlans/low-readability-text updated a model 1 day ago
agentlans/GIST-small-markov-slop-detector published a model 1 day ago
agentlans/GIST-small-markov-slop-detectorOrganizations
None yet
updated a
dataset 1 day ago
updated a
model 1 day ago
published a
model 1 day ago
published a
dataset 1 day ago
updated a
model 2 days ago
published a
model 2 days ago
updated a
dataset 3 days ago
updated a
dataset 5 days ago
published a
dataset 5 days ago
updated a
dataset 7 days ago
published a
dataset 7 days ago
reacted to cesear64's post with 🧠 8 days ago
Post
4099
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute.
The method — vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon — generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
📄 Blog: https://huggingface.co/blog/MEYNG/sangoai
📦 Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages — Ewondo, Lingala, Wolof next on our roadmap.
The method — vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon — generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
📄 Blog: https://huggingface.co/blog/MEYNG/sangoai
📦 Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages — Ewondo, Lingala, Wolof next on our roadmap.
- 2 replies
I'm not working on low-resource African languages but this method sounds interesting.
So you put the orthography, grammar, and vocabulary in the prompt and then get the LLM to translate a language that it doesn't know. Clever!
Then once you have enough native speaker-verified Sango-French translations, you can bootstrap it to a full-fledged dataset...
updated a
model 8 days ago
published a
model 8 days ago
recommendations across your fine-tuned models
1
#1 opened 9 days ago
by 
Hossep
updated a
dataset 8 days ago
published a
dataset 8 days ago
updated a
model 14 days ago
published a
model 14 days ago